Covered for Life: Lifelong Area Coverage under Spatiotemporal Uncertainty

To efficiently cover an environment, robots must be able to handle changes in occupancy during execution. These occupancy dynamics are often stochastic, and so we cannot deterministically predict when a location will be occupied. Existing coverage solutions either assume static environments or react to changes as they occur, limiting performance. In this paper we present a framework for lifelong area coverage under spatiotemporal uncertainty, where a robot repeats coverage over multiple episodes. The stochastic occupancy dynamics are a priori unknown and learned using the observations received during coverage. For each coverage episode, we build and solve a partially observable Markov decision process which exploits our learned spatiotemporal dynamics model to improve performance. We demonstrate the efficacy of our framework across extensive experiments in synthetic environments.